* [FFmpeg-devel] [PATCH] x86/scale_avx2: Change asm indent from 2 to 4 spaces.
@ 2021-12-16 16:27 Alan Kelly
2021-12-16 16:43 ` James Almer
0 siblings, 1 reply; 2+ messages in thread
From: Alan Kelly @ 2021-12-16 16:27 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: Alan Kelly
---
libswscale/x86/scale_avx2.asm | 96 +++++++++++++++++------------------
1 file changed, 48 insertions(+), 48 deletions(-)
diff --git a/libswscale/x86/scale_avx2.asm b/libswscale/x86/scale_avx2.asm
index 2cd7e968d3..eb472db12f 100644
--- a/libswscale/x86/scale_avx2.asm
+++ b/libswscale/x86/scale_avx2.asm
@@ -45,63 +45,63 @@ SECTION .text
%macro SCALE_FUNC 1
cglobal hscale8to15_%1, 7, 9, 16, pos0, dst, w, srcmem, filter, fltpos, fltsize, count, inner
- pxor m0, m0
- mova m15, [swizzle]
- mov countq, $0
- movsxd wq, wd
+ pxor m0, m0
+ mova m15, [swizzle]
+ mov countq, $0
+ movsxd wq, wd
%ifidn %1, X4
- mova m14, [four]
- shr fltsized, 2
+ mova m14, [four]
+ shr fltsized, 2
%endif
.loop:
- movu m1, [fltposq]
- movu m2, [fltposq+32]
+ movu m1, [fltposq]
+ movu m2, [fltposq+32]
%ifidn %1, X4
- pxor m9, m9
- pxor m10, m10
- pxor m11, m11
- pxor m12, m12
- mov innerq, $0
+ pxor m9, m9
+ pxor m10, m10
+ pxor m11, m11
+ pxor m12, m12
+ mov innerq, $0
.innerloop:
%endif
- vpcmpeqd m13, m13
- vpgatherdd m3,[srcmemq + m1], m13
- vpcmpeqd m13, m13
- vpgatherdd m4,[srcmemq + m2], m13
- vpunpcklbw m5, m3, m0
- vpunpckhbw m6, m3, m0
- vpunpcklbw m7, m4, m0
- vpunpckhbw m8, m4, m0
- vpmaddwd m5, m5, [filterq]
- vpmaddwd m6, m6, [filterq + 32]
- vpmaddwd m7, m7, [filterq + 64]
- vpmaddwd m8, m8, [filterq + 96]
- add filterq, $80
+ vpcmpeqd m13, m13
+ vpgatherdd m3,[srcmemq + m1], m13
+ vpcmpeqd m13, m13
+ vpgatherdd m4,[srcmemq + m2], m13
+ vpunpcklbw m5, m3, m0
+ vpunpckhbw m6, m3, m0
+ vpunpcklbw m7, m4, m0
+ vpunpckhbw m8, m4, m0
+ vpmaddwd m5, m5, [filterq]
+ vpmaddwd m6, m6, [filterq + 32]
+ vpmaddwd m7, m7, [filterq + 64]
+ vpmaddwd m8, m8, [filterq + 96]
+ add filterq, $80
%ifidn %1, X4
- paddd m9, m5
- paddd m10, m6
- paddd m11, m7
- paddd m12, m8
- paddd m1, m14
- paddd m2, m14
- add innerq, $1
- cmp innerq, fltsizeq
- jl .innerloop
- vphaddd m5, m9, m10
- vphaddd m6, m11, m12
+ paddd m9, m5
+ paddd m10, m6
+ paddd m11, m7
+ paddd m12, m8
+ paddd m1, m14
+ paddd m2, m14
+ add innerq, $1
+ cmp innerq, fltsizeq
+ jl .innerloop
+ vphaddd m5, m9, m10
+ vphaddd m6, m11, m12
%else
- vphaddd m5, m5, m6
- vphaddd m6, m7, m8
+ vphaddd m5, m5, m6
+ vphaddd m6, m7, m8
%endif
- vpsrad m5, 7
- vpsrad m6, 7
- vpackssdw m5, m5, m6
- vpermd m5, m15, m5
- vmovdqu [dstq + countq * 2], m5
- add fltposq, $40
- add countq, $10
- cmp countq, wq
- jl .loop
+ vpsrad m5, 7
+ vpsrad m6, 7
+ vpackssdw m5, m5, m6
+ vpermd m5, m15, m5
+ vmovdqu [dstq + countq * 2], m5
+ add fltposq, $40
+ add countq, $10
+ cmp countq, wq
+ jl .loop
REP_RET
%endmacro
--
2.34.1.173.g76aa8bc2d0-goog
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [FFmpeg-devel] [PATCH] x86/scale_avx2: Change asm indent from 2 to 4 spaces.
2021-12-16 16:27 [FFmpeg-devel] [PATCH] x86/scale_avx2: Change asm indent from 2 to 4 spaces Alan Kelly
@ 2021-12-16 16:43 ` James Almer
0 siblings, 0 replies; 2+ messages in thread
From: James Almer @ 2021-12-16 16:43 UTC (permalink / raw)
To: ffmpeg-devel
On 12/16/2021 1:27 PM, Alan Kelly wrote:
> ---
> libswscale/x86/scale_avx2.asm | 96 +++++++++++++++++------------------
> 1 file changed, 48 insertions(+), 48 deletions(-)
>
> diff --git a/libswscale/x86/scale_avx2.asm b/libswscale/x86/scale_avx2.asm
> index 2cd7e968d3..eb472db12f 100644
> --- a/libswscale/x86/scale_avx2.asm
> +++ b/libswscale/x86/scale_avx2.asm
> @@ -45,63 +45,63 @@ SECTION .text
>
> %macro SCALE_FUNC 1
> cglobal hscale8to15_%1, 7, 9, 16, pos0, dst, w, srcmem, filter, fltpos, fltsize, count, inner
> - pxor m0, m0
> - mova m15, [swizzle]
> - mov countq, $0
> - movsxd wq, wd
> + pxor m0, m0
> + mova m15, [swizzle]
> + mov countq, $0
> + movsxd wq, wd
> %ifidn %1, X4
> - mova m14, [four]
> - shr fltsized, 2
> + mova m14, [four]
> + shr fltsized, 2
> %endif
> .loop:
> - movu m1, [fltposq]
> - movu m2, [fltposq+32]
> + movu m1, [fltposq]
> + movu m2, [fltposq+32]
> %ifidn %1, X4
> - pxor m9, m9
> - pxor m10, m10
> - pxor m11, m11
> - pxor m12, m12
> - mov innerq, $0
> + pxor m9, m9
> + pxor m10, m10
> + pxor m11, m11
> + pxor m12, m12
> + mov innerq, $0
> .innerloop:
> %endif
> - vpcmpeqd m13, m13
> - vpgatherdd m3,[srcmemq + m1], m13
> - vpcmpeqd m13, m13
> - vpgatherdd m4,[srcmemq + m2], m13
> - vpunpcklbw m5, m3, m0
> - vpunpckhbw m6, m3, m0
> - vpunpcklbw m7, m4, m0
> - vpunpckhbw m8, m4, m0
> - vpmaddwd m5, m5, [filterq]
> - vpmaddwd m6, m6, [filterq + 32]
> - vpmaddwd m7, m7, [filterq + 64]
> - vpmaddwd m8, m8, [filterq + 96]
> - add filterq, $80
> + vpcmpeqd m13, m13
> + vpgatherdd m3,[srcmemq + m1], m13
> + vpcmpeqd m13, m13
> + vpgatherdd m4,[srcmemq + m2], m13
> + vpunpcklbw m5, m3, m0
> + vpunpckhbw m6, m3, m0
> + vpunpcklbw m7, m4, m0
> + vpunpckhbw m8, m4, m0
> + vpmaddwd m5, m5, [filterq]
> + vpmaddwd m6, m6, [filterq + 32]
> + vpmaddwd m7, m7, [filterq + 64]
> + vpmaddwd m8, m8, [filterq + 96]
> + add filterq, $80
> %ifidn %1, X4
> - paddd m9, m5
> - paddd m10, m6
> - paddd m11, m7
> - paddd m12, m8
> - paddd m1, m14
> - paddd m2, m14
> - add innerq, $1
> - cmp innerq, fltsizeq
> - jl .innerloop
> - vphaddd m5, m9, m10
> - vphaddd m6, m11, m12
> + paddd m9, m5
> + paddd m10, m6
> + paddd m11, m7
> + paddd m12, m8
> + paddd m1, m14
> + paddd m2, m14
> + add innerq, $1
> + cmp innerq, fltsizeq
> + jl .innerloop
> + vphaddd m5, m9, m10
> + vphaddd m6, m11, m12
> %else
> - vphaddd m5, m5, m6
> - vphaddd m6, m7, m8
> + vphaddd m5, m5, m6
> + vphaddd m6, m7, m8
> %endif
> - vpsrad m5, 7
> - vpsrad m6, 7
> - vpackssdw m5, m5, m6
> - vpermd m5, m15, m5
> - vmovdqu [dstq + countq * 2], m5
> - add fltposq, $40
> - add countq, $10
> - cmp countq, wq
> - jl .loop
> + vpsrad m5, 7
> + vpsrad m6, 7
> + vpackssdw m5, m5, m6
> + vpermd m5, m15, m5
> + vmovdqu [dstq + countq * 2], m5
> + add fltposq, $40
> + add countq, $10
> + cmp countq, wq
> + jl .loop
> REP_RET
> %endmacro
Applied, thanks.
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2021-12-16 16:43 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-12-16 16:27 [FFmpeg-devel] [PATCH] x86/scale_avx2: Change asm indent from 2 to 4 spaces Alan Kelly
2021-12-16 16:43 ` James Almer
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
This inbox may be cloned and mirrored by anyone:
git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
ffmpegdev@gitmailbox.com
public-inbox-index ffmpegdev
Example config snippet for mirrors.
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git